© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 241683
    Prev
    Next
    INDEX
    Explanations

    Birthday Party

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    戦
    0.48
    武
    0.44
     successively
    0.41
    開始
    0.41
    ឆ្នាំ
    0.40
    th
    0.40
    第二
    0.40
    紛
    0.40
    seq
    0.39
    海底
    0.39
    POSITIVE LOGITS
     umani
    0.55
     völl
    0.53
     hảo
    0.52
     conforto
    0.52
     rusk
    0.52
     Vestone
    0.49
    ধু
    0.46
     entendimento
    0.46
    ᐈ
    0.45
     Doremi
    0.45
    Activations Density 0.000%

    No Known Activations